ResearchDatasetsTOMATO-STARTOMATO-STARFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsHypothesis compositionTOMATO-STAR (test)5.16Total4Inspiration RetrievalTOMATO-STAR October 2025 (test)54.37Accuracy3